AI ethics evidence index Search
Source-linked daily record
Evidence record 3453 · automatically gathered

Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences

Federated Learning (FL) offers a privacy-preserving pathway for aligning Large Language Models (LLMs); however, existing frameworks typically enforce a monolithic reward model, inevitably averaging out inherently conflicting user preferences (e.g., helpfulness vs. harmlessness). While Variational Preference Learning (VPL) offers a pathway to personalization, adapting it to decentralized settings presents a fundamental challenge: posterior collapse driven by severe local data scarcity and heterog

Record details

Published: 29 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Privacy
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Shared topic: Safety & alignment · Shared topic: Privacy

Differentially Private Preference Data Synthesis for Large Language Model Alignment

arXiv · 29 May 2026

Shared topic: Safety & alignment · Shared topic: Privacy

Silent Failures in Federated Personalization of Foundation Models

arXiv · 31 May 2026

Shared topic: Safety & alignment · Shared topic: Privacy

The Concept Allocation Zone: Tracking How Concepts Form Across Transformer Depth

arXiv · 24 May 2026

Shared topic: Safety & alignment · Shared topic: Privacy

Measuring the Depth of LLM Unlearning via Activation Patching

arXiv · 23 May 2026

Shared topic: Safety & alignment · Shared topic: Privacy

Limited Marginal Benefit of Reasoning-Heavy LLM Deployment in ESG Narrative Scoring: A 4-Model Consensus Study on Japanese Listed Firms

arXiv · 22 May 2026

Shared topic: Safety & alignment · Shared topic: Privacy

How Far Will They Go? Red-Teaming Online Influence with Large Language Models

arXiv · 20 May 2026

How to cite this record

ethics.ai (29 May 2026), “Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences,” evidence record 3453, https://ethics.ai/record/3453 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.